What, Where and How? Introducing pose manifolds for industrial object manipulation
作者：
Highlights：
• A novel method for object grasping.
• Unified grasping system capable of answering queries such as What, Where and How.
• “What” is handled by a state-of-the-art object recognition framework.
• “Where” is answered by a manifold modeling-based 6 DoF pose estimation technique.
• “How” is tackled through an ontology-based semantic categorization.
摘要
•A novel method for object grasping.•Unified grasping system capable of answering queries such as What, Where and How.•“What” is handled by a state-of-the-art object recognition framework.•“Where” is answered by a manifold modeling-based 6 DoF pose estimation technique.•“How” is tackled through an ontology-based semantic categorization.
论文关键词：Object grasping,Object recognition,Pose estimation,Ontology-based semantic categorization
论文评审过程：Available online 3 July 2015, Version of Record 14 July 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.06.039
